Does Typological Blinding Impede Cross-Lingual Sharing?

Johannes Bjerva, Isabelle Augenstein

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

Abstrakt

Bridging the performance gap between high- and low-resource languages has been the focus of much previous work. Typological features from databases such as the World Atlas of Language Structures (WALS) are a prime candidate for this, as such data exists even for very low-resource languages. However, previous work has only found minor benefits from using typological information. Our hypothesis is that a model trained in a cross-lingual setting will pick up on typological cues from the input data, thus overshadowing the utility of explicitly using such features. We verify this hypothesis by blinding a model to typological information, and investigate how cross-lingual sharing and performance is impacted. Our model is based on a cross-lingual architecture in which the latent weights governing the sharing between languages is learnt during training. We show that (i) preventing this model from exploiting typology severely reduces performance, while a control experiment reaffirms that (ii) encouraging sharing according to typology somewhat improves performance.
OriginalsprogEngelsk
TitelProceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics
ForlagAssociation for Computational Linguistics
Publikationsdato21 apr. 2021
StatusE-pub ahead of print - 28 jan. 2021
BegivenhedConference of the European Chapter
of the Association for Computational Linguistics
-
Varighed: 21 apr. 202123 apr. 2021
Konferencens nummer: 16
https://2021.eacl.org/

Konference

KonferenceConference of the European Chapter
of the Association for Computational Linguistics
Nummer16
Periode21/04/202123/04/2021
Internetadresse

Fingeraftryk Dyk ned i forskningsemnerne om 'Does Typological Blinding Impede Cross-Lingual Sharing?'. Sammen danner de et unikt fingeraftryk.

Citationsformater